CognitionNet: A Collaborative Neural Network for Play Style Discovery in Online Skill Gaming Platform

TL;DR

This work tackles the challenge of uncovering player psychology and tactics from telemetry in online skill gaming by modeling sequences of game actions as micro-patterns that aggregate into play styles. It introduces CognitionNet, a dual-network architecture where a seq2seq interpreter mines micro-patterns and a supervised classifier aggregates them to predict engagement classes, connected via a novel Bridge loss that enables end-to-end training across different input dimensions. The approach yields interpretable behavior clusters and transitions, demonstrated on Rummy data, with improved engagement predictions and a taxonomy of play styles (e.g., Masterminds, Trailing Daredevils, Strugglers) that links micro-patterns to actionable insights. This framework offers a principled path to explainable, psychology-informed gaming analytics, enabling targeted interventions to enhance player experience and protection.

Abstract

Games are one of the safest source of realizing self-esteem and relaxation at the same time. An online gaming platform typically has massive data coming in, e.g., in-game actions, player moves, clickstreams, transactions etc. It is rather interesting, as something as simple as data on gaming moves can help create a psychological imprint of the user at that moment, based on her impulsive reactions and response to a situation in the game. Mining this knowledge can: (a) immediately help better explain observed and predicted player behavior; and (b) consequently propel deeper understanding towards players' experience, growth and protection. To this effect, we focus on discovery of the "game behaviours" as micro-patterns formed by continuous sequence of games and the persistent "play styles" of the players' as a sequence of such sequences on an online skill gaming platform for Rummy. We propose a two stage deep neural network, CognitionNet. The first stage focuses on mining game behaviours as cluster representations in a latent space while the second aggregates over these micro patterns to discover play styles via a supervised classification objective around player engagement. The dual objective allows CognitionNet to reveal several player psychology inspired decision making and tactics. To our knowledge, this is the first and one-of-its-kind research to fully automate the discovery of: (i) player psychology and game tactics from telemetry data; and (ii) relevant diagnostic explanations to players' engagement predictions. The collaborative training of the two networks with differential input dimensions is enabled using a novel formulation of "bridge loss". The network plays pivotal role in obtaining homogeneous and consistent play style definitions and significantly outperforms the SOTA baselines wherever applicable.

Figures (11)

• Figure 1: Random Forest Explainations using SHaP Model
• Figure 2: CognitionNet Architecture and Data/Loss Flow
• Figure 3: Bridge Loss Calculation Flow
• Figure 4: Comparison of Loss Trajectories in CognitionNet vs. DTCR-alike + Conv
• Figure 5: Evolving Adjacency Matrix with dropping Entropy